Skills
Navigate
skills/noorqureshi/security-skills/cloud-s3-exposure/Gen Agent Trust Hub

cloud-s3-exposure

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses command-line tools including awscli, gsutil, s3scanner, and gcpbucketbrute to interact with cloud environments. This includes network enumeration and file operations like reading from or writing to remote buckets. Evidence: SKILL.md specifies the use of aws s3 ls, aws s3 cp, and gsutil ls.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data sources to identify targets. 1. Ingestion points: The agent is instructed to extract bucket names from asset URLs, external JavaScript files, and DNS records in SKILL.md. 2. Boundary markers: No delimiters or warnings are used to prevent the agent from following instructions embedded in these external sources. 3. Capability inventory: The skill employs network-active tools (aws, gsutil) and file system access across SKILL.md. 4. Sanitization: There is no validation or filtering of the content extracted from external assets.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 10:30 AM